Smart emulator for wearable devices

• US 10,169,207 B2
• Filed: 02/15/2018
• Issued: 01/01/2019
• Est. Priority Date: 11/17/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bhuiya, Subhajit, Ekambaram, Vijay, Padilla, Donald A., Pandit, Sushain
• Primary Examiner(s): Chavis, John Q
• Application Number:
  US15/897,188
• Publication Number:
  US 20180150388A1
• Time in Patent Office: 320 Days
• Field of Search: 717124
• CPC Class Codes: G06F 11/3664 Environments for testing or debugging software
• CPC Class Codes: G06F 11/3684 for test design, e.g. generating new test cases

Abstract

Input of a video file is received. The video file includes video of a representation of a wearable device. One or more motion vector data is determined based on the video file. One or more motion sensor data is generated based on the motion vector data. One or more test results are determined using the motion sensor data. The video file, the motion vector data, and the motion sensor data are stored.

Claims

1. A method for generating data for testing applications designed for wearable devices via an emulator, the method comprising:

receiving, by one or more computer processors, an input of a video file, wherein;

the video file includes video of a test device being moved to mimic movements of a wearable device as worn by a user;

determining, by one or more computer processors, motion vector data, based on the video file, using video motion detection (VMD);

generating, by one or more computer processors, motion sensor data based on the determined motion vector data, wherein generating the motion sensor data based on the determined motion vector data comprises;

determining, by one more computer processors, an initial weight for each motion vector in the determined motion vector data, wherein the initial weight is determined based on an approach selected from the group consisting of;

selecting equal weights, selecting random weights, user input, and historical data;

determining, by one or more computer processors, a final weight for each motion vector in the determined motion vector data, wherein;

a machine-learning algorithm is used to determine the final weight for each motion vector in the determined motion vector data;

the machine-learning algorithm is selected from the group consisting of;

artificial neural networks, decision trees, random forests, nearest neighbors, and Apriori algorithm; and

the machine-learning algorithm is run iteratively starting with the initial weight for each motion vector in the determined motion vector data in order to determine the final weight; and

generating, by one or more computer processors, one or more rules that best fit the determined motion vector data, wherein;

the generated one or more rules are based on the final weight for each motion vector in the determined motion vector data;

the generated one or more rules allow for conversion of the motion vector data to the motion sensor data; and

generating the one or more rules that best fit the determined motion vector data comprises;

mapping, by one or more computer processors, existing motion vector data to motion sensor data, wherein the mapping is an offline labelling process using cognitive analysis;

labelling, by one or more computer processors, new motion vector data with corresponding motion sensor values based on a mapping of the existing motion vector data to motion sensor data; and

generating, by one or more computer processors, one or more rules that define a relationship between motion vector displacement and motion sensor displacement based on the new motion vector data labelled with corresponding motion sensor values;

determining, by one or more computer processors, one or more test results using the generated motion sensor data;

storing, by one or more computer processors, the video file, the motion vector data, and the motion sensor data, and the one or more rules;

receiving, by one or more computer processors, an indication of an application to be tested, wherein;

the application to be tested uses one or more motion sensors included in the wearable device; and

the application to be tested is a fitness application;

retrieving, by one or more computer processors, the motion sensor data associated with the application to be tested, wherein the association of the motion sensor data to the application to be tested is based on receiving the motion sensor data that corresponds to one or more sensors included in the wearable device;

causing, by one or more processors, an emulator to test the application, using the retrieved motion sensor data associated with the application to be tested, wherein the emulator uses respective motion sensor data, corresponding to each sensor that is used by the application;

determining, by one or more computer processors, one or more test results based on the retrieved motion sensor data; and

storing, by one or more computer processors, the one or more test results.